Search

There is a need to transform our current food system if we are to feed the rapidly expanding global population while maintaining planetary health. Within the island of Ireland, there is an urgent need to diversify the foods that currently contribute to our populations' protein intake. A Shared Island Innovative Food System approach is required to achieve this in a manner that is sustainable and provides benefits to producers, consumers and other supply chain participants. The Protein-I project employs such an approach, with the paradigm focusing on production of plant food through to human health, while paying particular attention to the development of the rural bioeconomy. Using an interdisciplinary approach, the team will develop strategies to maximise sustainable plant protein production in a traceable/transparent fashion and assess the impact of changes to existing value chains and the development of new value chains for the rural economy. A smart supply chain technology solution tailored to the needs of the agri-food industry will be developed and tested. Additionally, we will co-design consumer-led approaches to diversify plant protein intake, model the impact of changes at the population level and perform human interventions to demonstrate efficacy in terms of achieving adequate nutrition and improved health. Comprehensive engagement with stakeholders is embedded throughout the whole project to embrace the multi-actor approach. Overall, the project will be a key step towards future-proofing our food system on the island of Ireland and moving towards protecting planetary and population health, within the context of a just transition.

There is a global challenge related to the increasing number of People with Dementia (PwD) and the diminishing capacity of governments, health systems, and caregivers to provide the best care for them. Cost-effective technology solutions that enable and ensure a good quality of life for PwD via monitoring and interventions have been investigated comprehensively in the literature. The objective of this study was to investigate the challenges with the design and deployment of a Smart Home In a Box (SHIB) approach to monitoring PwD wellbeing within a care home. This could then support future SHIB implementations to have an adequate and prompt deployment allowing research to focus on the data collection and analysis aspects. An important consideration was that most care homes do not have the appropriate infrastructure for installing and using ambient sensors. The SHIB was evaluated via installation in the rooms of PwD with varying degrees of dementia at Kirk House Care Home in Belfast. Sensors from the SHIB were installed to test their capabilities for detecting Activities of Daily Living (ADLs). The sensors used were: (i) thermal sensors, (ii) contact sensors, (iii) Passive Infrared (PIR) sensors, and (iv) audio level sensors. Data from the sensors were collected, stored, and handled using a ‘SensorCentral’ data platform. The results of this study highlight challenges and opportunities that should be considered when designing and implementing a SHIB approach in a dementia care home. Lessons learned from this investigation are presented in addition to recommendations that could support monitoring the wellbeing of PwD. The main findings of this study are: (i) most care home buildings were not originally designed to appropriately install ambient sensors, and (ii) installation of SHIB sensors should be adapted depending on the specific case of the care home where they will be installed. It was acknowledged that in addition to care homes, the homes of PwD were also not designed for an appropriate integration with ambient sensors. This study provided the community with useful lessons, that will continue to be applied to improve future implementations of the SHIB approach.

The scale of Internet of Things (IoT) systems has expanded in recent times and, in tandem with this, IoT solutions have developed symbiotic relationships with technologies, such as edge Computing. IoT has leveraged edge computing capabilities to improve the capabilities of IoT solutions, such as facilitating quick data retrieval, low latency response, and advanced computation, among others. However, in contrast with the benefits offered by edge computing capabilities, there are several detractors, such as centralized data storage, data ownership, privacy, data auditability, and security, which concern the IoT community. This study leveraged blockchain’s inherent capabilities, including distributed storage system, non-repudiation, privacy, security, and immutability, to provide a novel, advanced edge computing architecture for IoT systems. Specifically, this blockchain-based edge computing architecture addressed centralized data storage, data auditability, privacy, data ownership, and security. Following implementation, the performance of this solution was evaluated to quantify performance in terms of response time and resource utilization. The results show the viability of the proposed and implemented architecture, characterized by improved privacy, device data ownership, security, and data auditability while implementing decentralized storage.

Mesh Networking over time has gained increased traction within the Internet of Things. It enables mass collection of data while also establishing new signal transmission pathways to avoid unnecessary depletion factors such as Material Penetration or Environmental factors like Weather generated interference. However, Mesh Networks have a lower power consumption efficiency due to the transceiver nodes power division. This has a direct impact on the Received Signal Strength Indicator (RSSI) measurement. This power difference can, therefore, result in inaccuracies for applications that employ an RSSI Based location algorithm for user tracking to occur as these are designed for Peer-to-Peer (P2P) communication. Additionally, through chaining the source RSSI to any given endpoint it also becomes possible to provide an estimated endpoint destination distance measurement which could be applied for user location services within Emergency Response situations. This study, therefore, investigates the offset generated by Mesh networking. An average loss of 5.75 dBm for reception and an average loss of 6.577dBm for transmission was identified within the bridging node due to the power split. Additionally, when chaining the RSSI across 30.48 m, this offset was found to present an average decrease of power signal strength efficiency of 202% within the system setup when compared to that of the P2P setup.

This paper presents a study which evaluated the potential for using ultra-low altitude, unmanned aerial vehicles to deliver fifth-generation (5G) cellular connectivity, particularly into areas requiring short-term enhancement in coverage. Such short-term enhancement requirements may include large gatherings of people or during disaster scenarios where there may be service outages or a need for increased bandwidth. An evaluation of this approach was conducted with empirically generated results regarding signal quality and cellular coverage—illustrating the potential of using unmanned ultra-low altitude aerial vehicles to deliver 5G cellular mobile services. Specifically, channel gain, mean time delay of the received signals ( $\tau _{\textrm {mean}}$ ), and the root-mean-square spread of the delay ( $\tau _{\textrm {rms}}$ ) were investigated for two distinct user modes at three different drone heights for three selected environments—an open area (field), a tree-lined environment, and an enclosed area. Maximum likelihood estimates for the various drone heights, user modes, and operational environments were found to be Rician distributed for the received signal strength measurements, whereas $\tau _{\textrm {mean}}$ and $\tau _{\textrm {rms}}$ for the open and tree-lined environments were Weibull distributed with the enclosed area tests being lognormally distributed. The paper also investigates how the channel gain may be affected when operating in each of the various global bands allocated for mid-5G communications, namely, Europe, China, Japan, South Korea, and North America. These regional mid-5G band allocations were found to yield minimal variance for all the environments considered.

Security frameworks are used to determine the approach to managing a network that may be under attack. The DREAD model from Microsoft, for example, promotes a strategy that is defined according to the impact of the attack on Damage, Reproducibility, Exploitability, Affected users, and Discoverability (DREAD). Each DREAD metric is scored, and the subsequent priorities are used to influence a reaction to the attack. In the event that an identified attack is being carried out by a security auditor, otherwise known as a white hat hacker whose intention is not malicious, the attack may not contribute significant Damage when considered according to DREAD yet may be consuming resources and causing challenges for the network service provider in terms of their ability to fulfil all customer service-level agreements (SLAs). This is therefore an operational event that needs to be responded to when managing the network load yet not necessarily from a cybersecurity perspective—it could, however, be managed from perspective of either performance or security. As an element of a Fault, Configuration, Accounting, Performance and Security (FCAPS) management approach, a response to such an event may involve reacting to a potential performance compromise occurring for security reasons. The network operator or service provider does not need to know the reason why the network is heavily loaded and only needs to ensure sufficient resources to fulfil all SLAs. However, it is recognised that there is an opportunity to pre-emptively identify that the network may become loaded in portions due to the tendencies of people operating within the network, specifically from a cybersecurity perspective and in relation to their intentions. This is in recognition of the fact that people who attack networks have a propensity towards commonalities in their personal characteristics and that these factors can be the drivers behind their attacking of a network. In addition to categorising attackers according to their intention (i.e., black hat and malicious, grey hat and not malicious but may violate laws, or white hat and friendly), a further degree of categorisation is proposed in terms of those who: (1) have some personal pressure which is influencing their desire to carry out malevolent actions online, (2) are naturally highly intelligent and inquisitive, and (3) those who are mentally ill. In this chapter, an approach is proposed to manage the network by profiling the characteristics of users residing across it according to their propensity to carry out a cyber-attack. Furthermore, it is suggested to use this information to pre-empt their activity such that the SLAs for all customers will continue to be achieved throughout the SLA lifetime. This process will be facilitated through the way in which the SLAs are defined and the information collected during the service setup procedure.

The increase of mental illness cases around the world can be described as an urgent and serious global health threat. Around 500 million people suffer from mental disorders, among which depression, schizophrenia, and dementia are the most prevalent. Revolutionary technological paradigms such as the Internet of Things (IoT) provide us with new capabilities to detect, assess, and care for patients early. This paper comprehensively survey works done at the intersection between IoT and mental health disorders. We evaluate multiple computational platforms, methods and devices, as well as study results and potential open issues for the effective use of IoT systems in mental health. We particularly elaborate on relevant open challenges in the use of existing IoT solutions for mental health care, which can be relevant given the potential impairments in some mental health patients such as data acquisition issues, lack of self-organization of devices and service level agreement, and security, privacy and consent issues, among others. We aim at opening the conversation for future research in this rather emerging area by outlining possible new paths based on the results and conclusions of this work., Consejo Nacional de Ciencia y Tecnologia (CONACyT), Sonora Institute of Technology (ITSON) via the PROFAPI program PROFAPI_2020_0055, Spanish Ministry of Science, Innovation and Universities (MICINN) project "Advanced Computing Architectures and Machine Learning-Based Solutions for Complex Problems in Bioinformatics, Biotechnology and Biomedicine" RTI2018-101674-B-I00

Internet of Things (IoT) services, to date, have been managed through affordances made by service providers (SP) to data provider (DP) customers who supply data for hosting in a shared repository. Services provided to data consumers (DC), on the other hand, are not managed in a similar way, with DCs being able to access datasets without providing detail to track them. Typically, DCs are not paying customers, and subsequently receive a best-effort Quality of Service (QoS)—thus they are vulnerable in the current system to change in data availability. To promote continued growth of the IoT, it is anticipated that changes are required to the business model. This may result in greater levels of protection for DC customers and more guaranteeable levels of service. In this chapter we present an ontology which responds to the challenge of managing customer information and providing a service autonomously in response. An application of the ontology is contextualized using the smart city waste management domain.

The growth of Internet use due to the emergence of new paradigms including social media and the Internet of Things (IoT) has presented several challenges. Within the IoT paradigm, there are several domain-specific challenges, among which security is crucial. Billions of devices in the IoT ecosystem have the responsibility of generating, processing, and analyzing large volumes of data. This data may connect with organizations, services, billions of people and other devices. This high level of interconnectivity creates a complex and heterogeneous network which is challenging to adequately secure the IoT system. IoT devices are smart, diverse, portable, interoperable, often autonomous and deployed in distributed topology.Properly managing the identities of these IoT devices plays a critical role in achieving the security of the overall IoT ecosystem. Notably, existing identity management systems fail to satisfy the requirements of identity management for IoT devices. We present a novel solution for IoT devices identity management based on self-sovereign identity and underpinned by proven security offered by distributed ledger technology. This novel approach provides a secure, portable, decentralized, persistent, unique, interoperable, self-owned and self-controlled identity for IoT devices. A Device’s identity with all its relationships in the IoT system are securely managed throughout its entire lifecycle.

BACKGROUND There is a global challenge related to the increase in the number of people with dementia (PwD) and the diminishing capacity of governments, health systems, and caregivers to provide the best care for them. Cost-effective technology solutions that enable and ensure a good quality of life for PwD via monitoring patients and interventions have been investigated comprehensively in the literature. OBJECTIVE The objective of this study was to investigate the challenges with the design, deployment and functioning of a Smart Home In a Box (SHIB) approach to monitoring PwD wellbeing within a care home. This could then support future implementations and present further opportunities for the SHIB approach. An important consideration was that most care homes do not have the appropriate infrastructure for installing and using ambient sensors. METHODS The SHIB was evaluated via installation in the rooms of 3 PwD with varying degrees of dementia. Sensors from the SHIB were installed in the rooms of the PwD to test the capabilities of these sensors for detecting Activities of Daily Living (ADLs). The sensors used were: (i) thermal sensors, (ii) contact sensors, (iii) Passive Infrared (PIR) sensors, and (iv) audio level sensors. Data was collected, stored and handled using a ‘SensorCentral’ data platform. RESULTS This study highlighted challenges and opportunities that should be considered when installing and using a SHIB approach in a dementia care home. Lessons learned from this investigation are presented in addition to recommendations that could support the wellbeing monitoring of PwD. This study also presents results from initial data analysis and demonstrates how activities, falls and abnormal behaviors could be detected and acted upon. CONCLUSIONS This study was conducted by Ulster University’s Pervasive Computing Research Group (PCRG) as part of the Northern Ireland Connected Health Innovation Centre (NI-CHIC) project. The design, deployment and functioning of the SHIB approach within Kirk House Care Home in Belfast provided the community with useful lessons, that will continue to be applied to improve future implementations of the SHIB approach. Several challenges arose during the installation, functioning and data collection at Kirk House Care Home, for example, regarding the adaption of technology to a building that was not originally designed for the integration of ambient sensors. The main findings of this study are: (i) most care home buildings were not originally designed to appropriately install ambient sensors, and (ii) installation of SHIB sensors should be adapted depending on the specific case of the care home where they will be installed. It was acknowledged that in addition to care homes, the homes of dementia patients were also not designed for an appropriate integration with ambient sensors. Hence, another possible use of a SHIB approach.

Research interests spanning numerous domains increasingly rely upon computational systems which can store and process a large volume of variable data that is stored at high velocity –representing a big data problem. This is particularly notable within the domain of ubiquitous and pervasive computing. This domain increasingly relies on storage and retrieval of sensor data to enable outcomes such as predictive analytics and activity recognition. Several current big data platforms exist; however, they have a range of deficiencies including lack of generic interoperability with agnostic sensors and an absence of features supporting academic research. Due to these deficiencies a custom, research oriented, high performance, and big data platform was devised and implemented. This platform is called SensorCentral and is presented within this paper. SensorCentral provides a framework which enables interoperability with a large range of agnostic sensor devices whilst simultaneously providing features which support research. Research supporting features include; facility to define experiments, ability to annotate experimental instances via purpose-built mobile applications, integrated machine learning functionality, facility to export data sets, rule-based classification and an extensible platform. The flagship implementation of this platform has been in operation for over 28 months within a University research group and has been successfully integrated with a range of sensors from a variety of manufacturers. This implementation currently stores over 850 million records and has been central to several research and industrial projects. Future work will integrate this platform into the open data initiative enabling collaboration with the international community of researchers.

Currently, Internet of Things (IoT) devices can integrate into an existing network where they may interact with a myriad of other devices that may host a range of capabilities. Such IoT devices may need to share data that is consumed by other devices or services. This data is generated by the capabilities built into devices within the ecosystem. A typical IoT ecosystem that is heterogeneous in nature should be able to have devices that offer a range of capabilities that could be explored in the event a device breakdown or malfunction. This is to ensure that the system is self-sustaining, and adequately perform during undesirable conditions. Hence, an IoT ecosystem should be able to collaborate, self-organize itself to explore these capabilities towards achieving an overall goal. As such, interoperability of these devices which will improve functionality, availability, and robustness of the IoT ecosystem must be achieved. Also, Several IoT representations today store their data centrally which gives rise to inherent issues such as single point of failure, and other possible vulnerabilities. Addressing these deficiencies alongside proper profiling of IoT device capability and other device details is viewed as the first stage in securing IoT ecosystems and this was explored in this research. This study presents the use of Distributed Ledger Technology which has the inherent property of being secure to profile the capability of IoT devices within self-organized IoT ecosystems. A system overview, data structures, and algorithms are presented.

The sedentary lifestyle, contributed to by long periods of sitting has been observed to have an impact on overall wellbeing. The longest period of sitting by an employee, in an office type setting, is at the desk therefore this is a primary contributor to health issues related to sedentary behaviour. This study presents and evaluates the technical aspects of an Internet of Things framework for monitoring wellbeing in the workplace. The framework is evaluated using "situation assessment" and "actuation" modules that suggest intervention strategies in a workplace environment for the improvement of wellbeing. A vital function of this framework is to accurately monitor the time an employee is sedentary. Based on evaluation results, it was observed that there was a maximum difference of 0.27% in activity level measured by the IoT framework when compared with manual monitoring techniques. The evaluation has demonstrated that the IoT framework was able to detect the duration of active and inactive phases of physical activity with a lower rate of error when compared with manual techniques for monitoring physical activity.

A sprawling and uncoordinated Internet of Things (IoT) environment has evolved in an uncontrolled manner where applications and infrastructure are made available as and when desired by operators, and, in many instances, without concern for others co-existing here. There is evidence already of IoT Service Providers changing their operational priorities and, as a result, the IoT may have an uncertain long-term future. This paper is driven by an assumption that an IoT environment with longevity will not be achieved using today's siloed systems; it is believed that these will not naturally mesh together without strategies in place to facilitate this. We therefore examine the reasons why and extent to which IoT technologies are generally not interoperable through the distinct ways that services are made available.

Activity recognition, a key component in pervasive healthcare monitoring, relies on classification algorithms that require labeled data of individuals performing the activity of interest to train accurate models. Labeling data can be performed in a lab setting where an individual enacts the activity under controlled conditions. The ubiquity of mobile and wearable sensors allows the collection of large datasets from individuals performing activities in naturalistic conditions. Gathering accurate data labels for activity recognition is typically an expensive and time-consuming process. In this paper we present two novel approaches for semi-automated online data labeling performed by the individual executing the activity of interest. The approaches have been designed to address two of the limitations of self-annotation: (i) The burden on the user performing and annotating the activity, and (ii) the lack of accuracy due to the user labeling the data minutes or hours after the completion of an activity. The first approach is based on the recognition of subtle finger gestures performed in response to a data-labeling query. The second approach focuses on labeling activities that have an auditory manifestation and uses a classifier to have an initial estimation of the activity, and a conversational agent to ask the participant for clarification or for additional data. Both approaches are described, evaluated in controlled experiments to assess their feasibility and their advantages and limitations are discussed. Results show that while both studies have limitations, they achieve 80% to 90% precision.

Patients with dementia often suffer from stress episodes that escalate to anxiety. This paper presents a feasibility study of using environmental smart microphones to detect anxiety in patients with dementia. It is based on the identified auditory manifestations of anxiety. To have a better understanding of the anxiety manifestations in patients with dementia, 70 diagnosed patients were observed in-situ and 4 caregivers were interviewed. The design of an environmental smart microphone called AnxiCare has been developed and it is introduced. Feasibility interviews regarding the use of AnxiCare were conducted with caregivers at a care residence in Spain. Results from the observations, interviews and a preliminary validation are presented.

Inadvertent falls can cause serious, and potentially fatal injuries, to at risk individuals. One such community of at-risk individuals is the elderly population where age related complications, such as osteoporosis and dementia, can further increase the incidence and negative impact of such falls. Notably, falls within that community has been identified as the leading cause of injury related preventable death, hospitalization and reduction to quality of life. In such cases, rapid detection of, and reaction, to fall events has shown to be critical to reduce the negative effects of falls within this community. Currently, a range of fall detection solutions exist, however, they have several deficiencies related to the core approach that has been adopted. This study has developed an ensemble of thermal vision-based, big data facilitated, solutions which aim to address some of these deficiencies. An evaluation of these logical and data-driven processes has occurred with the promising results presented within this manuscript. Finally, opportunities future work and real-world evaluation have occurred and are underway.

A Service Level Agreement (SLA) defines a contract between network service providers and consumers, specifying the terms of a service which providers will make available and the conditions which consumers will accept. To date, SLAs have been specified using basic terms, such as availability and network performance, with a consumer being compensated in the event that the service provided does not meet the terms agreed. Given changes in the ways which network services are now made available, however, SLA terms are changing to capture both the differences in service provision and, additionally, in the responsibilities of the parties involved. It is this aspect of information SLAs which we respond to in this work, and we propose a SLA model which accommodates the requirements of these new relationships. We also propose a set of metrics, a selection of which are presented in this paper to demonstrate our concept, and recommend that a selection can be adapted by consumers. Finally, due to the intricate relationships between data consumers and data providers in the IoT environment and the fact that metric adaptation may lead to SLA violation, we discuss SLA conflict resolution through prioritizing non-functional metrics on a per-customer basis.

Data annotation is the process of segmenting and labelling any type of data (images, audio or text). It is an important task for producing reliable datasets that can be used to train machine learning algorithms for the purpose of Activity Recognition. This paper presents the work in progress towards a semi-automated approach for collecting and annotating audio data from simple sounds that are typically produced at home when people perform daily activities, for example the sound of running water when a tap is open. We propose the use of an app called ISSA (Intelligent System for Sound Annotation) running on smart microphones to facilitate the semi-automated annotation of audible activities. When a sound is produced, the app tries to classify the activity and notifies the user, who can correct the classification and/or provide additional information such as the location of the sound. To illustrate the feasibility of the approach, an initial version of ISSA was implemented to train an audio classifier in a one-bedroom apartment.

The global population is aging in a never-before seen way, introducing an increasing ageing-related cognitive ailments, such as dementia. This aging is coupled with a reduction in the global support ratio, reducing the availability of formal and informal support and therefore capacity to care for those suffering these aging related ailments. Assistive Smart Homes (SH) are a promising form of technology enabling assistance with activities of daily living, providing support of suffers of cognitive ailments and increasing their independence and quality of life. Traditional SH systems have deficiencies that have been partially addressed by through goal-driven SH systems. Goal-driven SHs incorporate flexible activity models, goals, which partially address some of these issues. Goals may be combined to provide assistance with dynamic and variable activities. This paradigm-shift, however, introduces the need to provide dynamic assistance within such SHs. This study presents a novel approach to achieve this through video based content analysis and a mechanism to facilitate matching analysed videos to dynamic activities/goals. The mechanism behind this approach is detailed and followed by the presentation of an evaluation where showing promising results were shown.

The Open Data Initiative (ODI) has been previously proposed to facilitate the sharing of annotated datasets within the pervasive health care research community. This paper outlines the requirements for the ODI portal based on the ontological data model of the ODI and its typical usage scenarios. In the context of an action research framework, the paper outlines the ODI platform, the design of a prototype user interface for the purposes of initial evaluation and its technical review by third-party researchers (n = 3). The main findings from the technical review were found to be the need for a more flexible user interface to reflect the different experimental configurations in the research community, provision for describing dataset usage, and dissemination conditions. The technical review also identified the value of permitting datasets with variable quality, as noisy datasets are useful in the testing of activity recognition algorithms. Revisions to the ODI ontology and platform are proposed based on the findings from this study.

The global population is ageing, as a consequence of this there will be a greater incidence of ageing related illnesses which cause cognitive impairment–such as Alzheimer’s disease. Within residential care homes, such cognitive impairment can lead to wandering of individuals beyond the boundaries of safety provided. This wandering, particularly in urban areas can be life threatening. This study introduces a novel solution to detect, and alert caregivers of, egress of at-risk inhabitants of a care home. This solution operates through a combination of wearable Bluetooth beacons and beam-formed listening devices. In an evaluation process involving 275 egress events, this solution proved to offer accurate operation with no incidence of false positives. Notably, this solution has been deployed within a real residential care home environment for over 12 months. Proposed future work discusses improvements to this solution.

Gait velocity is an important measure of independence and functional ability to those within the older population. Detecting changes in gait velocity can aid to provide interventions to avoid hospitalisation, currently gait velocity is assessed in a clinical setting, where the patient is timed over a measured distance between 3-6 metres by a clinician, however, this is time consuming, subjective, and not possible to carry out frequently over time. An unobtrusive method of monitoring gait velocity, frequently, over extended periods of time, would therefore be advantageous when developing interventions. This paper proposes an unobtrusive computer vision-based method of continuously monitoring an occupants gait velocity within their own home. This is achieved through the use of a low cost thermal vision sensor. The system was benchmarked against the clinical standard method of being timed by a stopwatch. Results show a high correlation between the gait velocity measured by the thermal vision sensor and the measured stopwatch velocity (R=0.941, p=0.02).

This paper presents the strengths, weaknesses, opportunities, and threats for Artificial Intelligence (AI) as applied to long-term respiratory disease management. This analysis will help to identify, understand, and evaluate key aspects of the technology as well as the various internal/external forces which influence its success in this application space. Such understanding is instrumental to ensure judicial planning and implementation with suitable safeguards being considered. AI has the potential to radically change how respiratory disease management is conducted and may help clinicians to realise new treatment paradigms. The application of AI is clearly not specific to respiratory disease management; however it is a chronic disease that requires on-going monitoring and well evidenced decision making regarding treatment pathways or medication modification. This work emphasises the current position of AI as applied to respiratory disease management and identifies the issues to help develop strategic directions to ensure successful implementation, evidenced by ubiquitous acceptance and uptake.

This paper presents an advanced long-range low-power Internet of Things wearable temperature sensor to evaluate and predict the likelihood of a heart failure event in high-risk patients. Initial trials have validated the potential of long-range long-term personalized community-based monitoring with smart intervention decision making. The intelligent device implements machine learning to understand the user’s activities of Daily Living (ADL) and their environment; using this information coupled with their body temperature allows the system to evaluate and predict the likelihood of a heart failure event. The solution is based upon the European 868 MHz LoRaWAN standard. As Ulster University roll out a regional LoRaWAN “Things Connected” network across Northern Ireland (owned by Digital Catapult, UK) the embryonic solution will be tested on a larger scale for both home based monitoring as well as patients undertaking daily living activities.

Sedentary behavior has been linked to leading causes of morbidity and mortality, including cancer, cardiovascular disease and diabetes. Those who work in office workplaces are susceptible to higher levels of sedentary behavior during the working day. This paper introduces a novel approach to the detection of sedentary behavior through the use of a thermal sensor mounted on the ceiling above a busy workspace. This solution was found to more accurately record 7 out of 10 activity metrics in comparison to self-assessment, when compared to chair pressure sensor recordings.

Existing smart environment based alert solutions have adopted a relatively complex and tailored approach to supporting individuals. These solutions have involved sensor based monitoring, activity recognition and assistance provisioning. Traditionally they have suffered from a number of issues, rooted in scalability and performance, associated with complex activity recognition processes. This paper introduces a generic approach to realizing an alerting platform within a smart environment. The core concept of this approach is presented and placed within the context of related work. A description of the approach is provided, followed by an evaluation. This evaluation shows the approach offers reasonable accuracy, future work will increase accuracy.

Pervasive and ubiquitous computing increasingly relies on data-driven models learnt from large datasets. This learning process requires annotations in conjunction with datasets to prepare training data. Ambient Assistive Living (AAL) is one application of pervasive and ubiquitous computing that focuses on providing support for individuals. A subset of AAL solutions exist which model and recognize activities/behaviors to provide assistive services. This paper introduces an annotation mechanism for an AAL platform that can recognize, and provide alerts for, generic activities/behaviors. Previous annotation approaches have several limitations that make them unsuited for use in this platform. To address these deficiencies, an annotation solution relying on environmental NFC tags and smartphones has been devised. This paper details this annotation mechanism, its incorporation into the AAL platform and presents an evaluation focused on the efficacy of annotations produced. In this evaluation, the annotation mechanism was shown to offer reliable, low effort, secure and accurate annotations that are appropriate for learning user behaviors from datasets produced by this platform. Some weaknesses of this annotation approach were identified with solutions proposed within future work.

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. The global population is aging; projections show that by 2050, more than 20% of the population will be aged over 64. This will lead to an increase in aging related illness, a decrease in informal support, and ultimately issues with providing care for these individuals. Assistive smart homes provide a promising solution to some of these issues. Nevertheless, they currently have issues hindering their adoption. To help address some of these issues, this study introduces a novel approach to implementing assistive smart homes. The devised approach is based upon an intention recognition mechanism incorporated into an intelligent agent architecture. This approach is detailed and evaluated. Evaluation was performed across three scenarios. Scenario 1 involved a web interface, focusing on testing the intention recognition mechanism. Scenarios 2 and 3 involved retrofitting a home with sensors and providing assistance with activities over a period of 3 months. The average accuracy for these three scenarios was 100%, 64.4%, and 83.3%, respectively. Future will extend and further evaluate this approach by implementing advanced sensor-filtering rules and evaluating more complex activities.

Adoption of the pervasive and ubiquitous computing paradigm is increasing. One application of this paradigm is Ambient Assistive Living where ICT-based assistive services are deployed in an environment. In this study, a Smart Home in a Box (SHIB) has been devised as an AAL solution. This SHIB relies upon Internet of Things (IoT) devices, such as thermal vision sensors, within an environment to function. Each SHIB deployment consists of IoT devices taken from a common pool of devices. The exact device manifest of each SHIB deployment will change as dictated by end-user requirements. Additionally, this pool will grow and expand when devices are removed or added from previous SHIB deployments. To efficiently manage this pool of devices, and SHIB deployments, a remote management solution is required. Current remote management solutions have a range of deficiencies that render them unsuitable for use with the current SHIB platform. To address these deficiencies, a secure mechanism to manage the IoT devices has been devised. This paper presents this mechanism and evaluates its applicability to SHIB deployments. The evaluation focused on assessing the security of the mechanism and the viability of its Low-Power Wireless Wide-Area Network-based communications. This evaluation showed that the proposed solution was reliable and suitable for the intended deployment scenario. An extended evaluation and system improvements have been identified and proposed within future work.

Increasingly research interests within the area of pervasive and ubiquitous computing, such as activity recognition, rely upon storage and retrieval of sensor data. Due to the increase in volume, velocity and variation of such sensor data its storage and retrieval has become a big data problem. There are a number of current platforms that are intended to store large amount of sensor data, however, they lack research oriented features. To address these deficiencies this study introduces a research oriented, device agnostic sensor, data platform called SensorCentral. This platform incorporates several research oriented features such as offering annotation interfaces, metric generation, exporting experimental datasets, machine learning services, rule based classification, forwarding live sensor records to other systems and quick sensor configuration. The current main installation of this platform has been in place for over 18 months, has been successfully associated with 6 sensor classes from 13 vendors and currently holds over 500 million records. Future work will involve offering this platform to other researchers and incorporating direct integration with the Open Data Initiative enabling better collaboration with other researchers on an international scale.

It has been estimated, on a global scale, that a limb is lost every 20 s due to diabetes. Effective treatment has, however, been shown to reduce the risk of amputations and foot ulcers. Self-management and the provision of effective foot care in the clinic and at home, is viewed as instrumental in providing appropriate care for people with diabetes. This in turn can reduce the costs associated with treating and managing diabetes and its associated complications. This paper presents a usability evaluation of a smartphone based solution for the management of diabetic foot disease. The solution combines novel thermal imaging with tailored educational content and gamification elements in an attempt to improve self-management of the condition. The solution was evaluated in a workshop setting by 7 participants. Overall, the participants felt the proposed solution would be a very worthwhile endeavor. They rated the usability and utility at an acceptable level (SUS 69.1/100). Notable suggested improvements focused on how educational content was formatted and searched in addition to the physical support provided to facilitate imaging of the feet.

With the growing change to a more aged population and greater strain on our health care services, due to higher costs and demand, there is a growing need to develop solutions to help solve this health care crisis. Generally older people prefer to keep their independence as they age, which gives them a better quality of life. Independent living can be achieved both within care homes and at home, and with the assistance of technology this can be achieved more easily. In this study a Smart Home in a Box (SHIB) solution has been developed to support Ambient Assistive Living (AAL). This paper presents a solution for an interface to interact and be notified by the SHIB platform. A usability evaluation of the developed solution is also presented in the paper. This evaluation asked 8 people consisting of management staff and a Family and Relatives group from a care home, to determine how older people would feel about a solution like this. Overall the participants of the usability evaluation felt the developed solution would benefit older people living at home.

The Open Data Initiative (ODI) has previously been proposed as a framework for the collection, annotation, management and sharing of data gathered through research in pervasive health and smart environment systems. It includes the provision of open access protocols for the conduct of experiments and a standard format for the exchange of datasets. In this paper we formalize the structure of the ODI repository through development of an ontology which seeks to unify the representation of ODI objects, experimental protocols, and event logs. An XML-based standards approach to storing event logs, using eXtensible Event Stream (XES) enables data sharing, manipulation and ontology integration. Typical usage scenarios are presented based on published experimental data to validate the concepts of the presented work. Related SPARQL queries are used to illustrate the outputs which can be derived. Based on these initial results, we outline a system architecture for prototyping further ODI related work.

INTRODUCTION: Dementia is a syndrome characterised by a decline in memory, language, and problem-solving thataffects the ability of patients to perform everyday activities. Patients with dementia tend to experience episodes of anxietyand remain for extended periods, which affects their quality of life.OBJECTIVES: To design AnxiDetector, a system capable of detecting patterns of sounds associated before and during themanifestation of anxiety in patients with dementia.METHODS: We conducted a non-participatory observation of 70 diagnosed patients in-situ, and conducted semi-structuredinterviews with four caregivers at a residential centre. Using the findings from our observation and caregiver interviews, wedeveloped the AnxiDetector prototype and tested this in an experimental setting where we defined nine classes of audio torepresent two groups of sounds: (i) Disturbance which includes audio files that characterise sounds that trigger anxiety inpatients with dementia, and (ii) Expression which includes audio files that characterise sounds expressed by the patientsduring episodes of anxiety. We conducted two experimental classifications of sounds using (i) a Neural Network modeltrained and (ii) a Support Vector Machine model. The first evaluation consists of a binary discriminating between the twogroups of sounds; the second evaluation discriminates the nine classes of audio. The audio resources were retrieved frompublicly available datasets.RESULTS: The qualitative results present the views of the caregivers on the adoption of AnxiDetector. The quantitativeresults from our binary discrimination show a classification accuracy of 98.1% and 99.2% for the Deep Neural Network andSupport Vector Machine models, respectively. When classifying the nine classes of sound, our model shows a classificationaccuracy of 92.2%. Whereas, the Support Vector Machine model yielded an overall classification accuracy of 93.0%.CONCLUSION: In this paper, we presented the outcomes from an observational study in-site at a residential care centre,qualitative findings from interviews with caregivers, the design of AnxiDetector, and preliminary qualitative results of amethodology devised to detect relevant acoustic events associated with anxiety in patients with dementia. We conclude bysignalling future plans to conduct in-situ validation of the effectiveness of AnxiDetector for anxiety detection.

Accidental falls can cause serious injury to at risk individuals. This is especially true in the elderly community where falls are the leading cause of hospitalization, injury-related deaths and loss of independence. Detecting and rapidly responding to falls has shown to reduce the long-term impact of and risks associated with falls. A number of real time fall detection solutions exist, however, these have some deficiencies relating to privacy, maintenance, and correct usage. This study introduces a novel fall detection approach that aims to address some of these deficiencies through use of computer vision processes and ceiling mounted thermal vision sensors. A preliminary evaluation has been performed on this process showing promising results, with an accuracy of 68 %, however, highlighting a number of issues related to false positives. Future work will improve this approach and provide extended evaluation.

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. Current activity recognition based assistive living solutions have adopted relatively rigid models of inhabitant activities. These solutions have some deficiencies associated with the use of these models. To address this, a goal-oriented solution has been proposed. In a goal-oriented solution, goal models offer a method of flexibly modelling inhabitant activity. The flexibility of these goal models can dynamically produce a large number of varying action plans that may be used to guide inhabitants. In order to provide illustrative, video-based, instruction for these numerous actions plans, a number of video clips would need to be associated with each variation. To address this, rich metadata may be used to automatically match appropriate video clips from a video repository to each specific, dynamically generated, activity plan. This study introduces a mechanism of automatically generating suitable rich metadata representing actions depicted within video clips to facilitate such video matching. This performance of this mechanism was evaluated using eighteen video files; during this evaluation metadata was automatically generated with a high level of accuracy.

Musculoskeletal injuries are common and costly. Ankle sprains are one of the most common such injuries, carrying significant risk of persistent disabling symptoms. Rehabilitation has been shown to be more effective than standard conservative approaches for musculoskeletal injuries. The use of a mobile app to present rehabilitation guidance may offer a more accessible, engaging and effective solution to ankle sprain rehabilitation. Many existing apps target the prevention and rehabilitation of ankle sprains, however, evaluation details are limited. This paper presents ReApp, a novel app for the rehabilitation of ankle sprain. Full details of the app implementation are provided, in addition to details of the results from a three phase evaluation process involving technical (n = 5), clinical (n = 6) and end-users (n = 7). Results from the evaluation were positive, and feedback was used to improve the app.

Autism spectrum disorder ASD is a condition that is being diagnosed in a growing portion of the population. ASD represents a range of complex disorders with a number of symptoms including social difficulties and behavioral issues. Some individuals suffering from ASD are prone to incidents of agitation that can lead to escalation and meltdowns. Such incidents represent a risk to the individuals with ASD and others who share their environment. This paper introduces a novel approach to monitor triggers for these incidents with an aim to detect and predict an incident happening. Non-invasive sensors monitor factors within an environment that may indicate such an incident. Combined with an NFC and smart phone based mechanism to report incidents in a relatively friction free manner. These reports will be combined with sensor records to train a prediction system based on supervised machine learning. Future work will identify the best performing machine-learning technique and will evaluate the approach.

Current assistive smart homes have adopted a relatively rigid approach to modeling activities. The use of these activity models have introduced factors which block adoption of smart home technology. To address this, goal driven smart homes have been proposed, these are based upon more flexible activity structures. However, this goal-driven approach does have a disadvantage where flexibility in this activity modeling can lead to difficulty providing illustrative guidance. To address this, a video analysis and nomination mechanism is required to provide suitable assistive clips for a given goal. This paper introduces a novel mechanism for nominating a suitable video clip given a pool of automatically generated metadata. This mechanism was then evaluated using a voice based assistant application and a tool emulating assistance requests by a goal-driven smart home. The initial evaluation produced promising results.

Context-aware applications within pervasive environments are increasingly being developed as services and deployed in the cloud. As such these services are increasingly required to be adaptive to individual users to meet their specific needs or to reflect the changes of their behavior. To address this emerging challenge this paper introduces a service-oriented personalisation framework for service personalisation with special emphasis being placed on behavior learning for user model and service function adaptation. The paper describes the system architecture and the underlying methods and technologies including modelling and reasoning, behavior analysis and a personalisation mechanism. The approach has been implemented in a service-oriented prototype system, and evaluated in a typical scenario of providing personalised travel assistance for the elderly using the help-on-demand services deployed on smartphone.

The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. Existing assistive living and prompting based solutions have adopted a relatively complex approach to supporting individuals. These solutions have involved sensor based monitoring, activity recognition and assistance provisioning. Traditionally they have suffered from a number of issues rooted in scalability and performance levels associated with the activity recognition process. This paper introduces a simplistic approach to assistive living within a user's residence through the use of NFC tags and smart devices. The core concept of this approach is presented and is subsequently placed within the context of related work. A description of the architecture is provided and results following technical evaluation of the first system prototype are discussed.

Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.